Borrowing it
Nothing to install: this file belongs to st0012/cctop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/st0012/cctop/master/.claude/skills/e2e-session-test/SKILL.mdgit clone --depth 1 https://github.com/st0012/cctopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/st0012/cctop/e2e-session-test)<a href="https://agentmods.dev/skills/st0012/cctop/e2e-session-test"><img src="https://agentmods.dev/badge/skills/st0012/cctop/e2e-session-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/st0012/cctop/e2e-session-test"><img src="https://agentmods.dev/badge/skills/st0012/cctop/e2e-session-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 31 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00112 | $0.00753 |
| Opus 5.5 | $0.00045 | $0.00301 |
| Sonnet 5.5 | $0.00022 | $0.00151 |
| Haiku 4.5 | $0.00011 | $0.00075 |
Grade A, and why
e2e-session-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cctop end-to-end session test
Verify a real session flows all the way through:
agent in a terminal → cctop hooks → ~/.cctop/sessions/<pid>.json → panel card
A good smoke test after touching hooks, the session schema, or the panel.
Capabilities, not tools
Harness-agnostic — it needs three generic capabilities. Use your environment's equivalent; don't assume a specific tool:
- run shell commands
- capture a screenshot of the screen (or fall back to the
screencaptureCLI) - view an image you captured
Create the session with a CLI agent in a terminal
Drive a CLI agent (claude / codex / opencode / pi) in a terminal window —
it's a real session and one shell command starts it. Don't try to puppet a
desktop agent's GUI: if it's the app hosting you, screen capture hides its window
and you can't confirm input landed (see references/troubleshooting.md). Requires a
cctop build with the cctop:// URL scheme (ships with this skill).
Steps (run from the repo root)
# 1. Baseline — note the PIDs
.claude/skills/e2e-session-test/scripts/cctop-sessions.sh
# 2. Create a session — opens a terminal running the agent, waits for it to register
.claude/skills/e2e-session-test/scripts/launch-cli-session.sh claude ~/projects/cctop
# 3. Verify — a new PID entry with the right source (cc/codex/opencode/pi) appears
.claude/skills/e2e-session-test/scripts/cctop-sessions.sh
# 4. Summon the panel
open cctop://toggle
Then capture a screenshot and confirm the new session's card is in the panel
(right status, source, project). Run open cctop://toggle again to close it — a
clean closed/open pair if you want before/after proof. For a shareable record,
write a small HTML log embedding the screenshots.
Two details the launcher handles, because they otherwise make this fail silently: a
login shell (so the agent's PATH, e.g. ~/.local/bin, resolves) and a
trusted directory (so the agent doesn't stall at a folder-trust prompt).
open cctop://toggle is used instead of a menu-bar click or hotkey because those
need extra OS permissions under automation.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 74 lines · 112 tokens per session scan A f1fb73829200
e2e-session-test is a skill published in the GitHub repository st0012/cctop (159 stars, last pushed 22d ago), licensed MIT. It adds 112 tokens to every session and 753 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
press-clip
Turn a live article URL into a press clip that looks like the real coverage — the publication's own logo, fonts, photos and layout kept intact, the ads and clutter removed, and (for a roundup) just the client's section. Renders to PDF. You inspect each site and tailor the removal; the bundled script carries no…
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
base
Universal coding patterns, constraints, TDD workflow, atomic todos.
agf
Find local coding-agent sessions, inspect bounded metadata or summaries, and prepare a read-only resume plan with AGF. Use for finding prior work across agent CLIs, not for executing agents, deleting sessions, or reading full transcripts.
long-running-work
Carrying complex coding and project work through commands that take minutes or hours: evals, benchmarks, full builds and test suites, migrations, servers, multi-round runs. Use when a command may run past a few minutes, timed out once, or when the task spans several rounds of run, read results, fix, run again.
test-documentation
Analyze, prioritize, and document test cases in TMS (Jira/Xray), or repair an existing Story-ATS-ATP-ATR-TC cascade through a sealed explicit mode. Use for Test/ATP/ATR artifacts, ROI and automation verdicts, maintaining traceability, fix-traceability, or broken TMS links. The repair-traceability mode audits, plans…